Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information
This work addresses the problem of maintaining consistent AI agent behavior and communication style in complex communication games for game AI developers.
This study developed an LLM-based AI agent for the Werewolf Game, focusing on improving the consistency of its utterances. The agent achieved contextual and tonal consistency throughout the game by leveraging LLM-generated dialogue summaries and manually designed personas and utterance examples.
The Werewolf Game is a communication game where players' reasoning and discussion skills are essential. In this study, we present a Werewolf AI agent developed for the AIWolfDial 2024 shared task, co-hosted with the 17th INLG. In recent years, large language models like ChatGPT have garnered attention for their exceptional response generation and reasoning capabilities. We thus develop the LLM-based agents for the Werewolf Game. This study aims to enhance the consistency of the agent's utterances by utilizing dialogue summaries generated by LLMs and manually designed personas and utterance examples. By analyzing self-match game logs, we demonstrate that the agent's utterances are contextually consistent and that the character, including tone, is maintained throughout the game.